LLM
A neural network trained on huge amounts of text, capable of generating, summarising, and reasoning about language.
We are working on a detailed page for LLM - covering why it matters, how it works, related terms, and the tools that use it.
Related terms
From the glossaryFrequently asked questions
Is every AI an LLM?+
No. LLMs are one type of AI model focused on text. Other AI models handle images, audio, video, or structured data prediction without being language models.
How big is a large language model?+
Size is measured in parameters, the numeric weights learned during training. Models range from a few million parameters for small local models to hundreds of billions for frontier models like GPT-4.
Can LLMs reason?+
They can simulate multi-step reasoning through chain-of-thought prompting, but current research debates whether this constitutes true reasoning or very sophisticated pattern matching.